scholarly journals Generating Realistic Morphologies of Neurons in Rodent Hippocampus with DCGAN

2018 ◽  
Author(s):  
Darian H. Hadjiabadi
Keyword(s):  
Computational Models ◽  
False Positive Rate ◽  
A Priori ◽  
Image Features ◽  
Generative Adversarial Network ◽  
Dendritic Trees ◽  
Form And Function ◽  
Adversarial Network ◽  
Positive Rate ◽  
And Function

AbstractDendritic size and branching patterns are important features of neural form and function. However, current computational models of neuronal networks use simplistic cylindrical geometries to mimic dendritic arborizations. One reason for this is that current methods to generate dendritic trees have rigid a priori constraints. To address this, a deep convolutional generative adversarial network (DCGAN) trained on images of rodent hippocampal granule and pyramidal dendritic trees. Image features learned by the network were used to generate realistic dendritic morphologies. Results show that DCGANs achieved greater stability∗ and high generalization, as quantified by kernel maximum mean discrepancy, when exposed to instance noise and/or label smoothing during training. Trained models successfully generated realistic morphologies for both neuron types, with high false positive rate reported by expert reviewers. Collectively, DCGANs offer a unique opportunity to advance the geometry of neural modeling, and, therefore, to propel our understanding of neuronal function.∗ A “stable/stabilized DCGAN”, as mentioned throughout this work, is a DCGAN which was stable throughout training.

Machine learning-based approach for segmentation of intervertebral disc degeneration from lumbar section of spine using MRI images

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Jayashri V. Shinde ◽  
Yashwant V. Joshi ◽  
Ramchandra R. Manthalkar ◽  
Joshi
Keyword(s):  
Intervertebral Disc ◽  
Nearest Neighbor ◽  
False Positive Rate ◽  
True Positive Rate ◽  
K Nearest Neighbor ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Grade Classification ◽  
Whale Optimization ◽  
Positive Rate

Abstract Objectives Intervertebral disc segmentation is one of the methods to diagnose spinal disease through the degeneration in asymptomatic and symptomatic patients. Even though numerous intervertebral disc segmentation techniques are available, classifying the grades in the intervertebral disc is a hectic challenge in the existing disc segmentation methods. Thus, an effective Whale Spine-Generative Adversarial Network (WSpine-GAN) method is proposed to segment the intervertebral disc for effective grade classification. Methods The proposed WSpine-GAN method effectively performs the disc segmentation, wherein the weights of Spine-GAN are optimally tuned using Whale Optimization Algorithm (WOA). Then, the refined disc features, such as pixel-based features and the connectivity features are extracted. Finally, the K-Nearest Neighbor (KNN) classifier based on the pfirrmann’s grading system performs the grade classification. Results The implementation of the grade classification strategy based on the proposed WSpine-GAN and KNN is performed using the real-time database, and the performance based on the metrics yielded the accuracy, true positive rate (TPR), and false positive rate (FPR) values of 97.778, 97.83, and 0.586% for the training percentage and 92.382, 90.580, and 1.972% for the K-fold value. Conclusions The proposed WSpine-GAN method effectively performs the disc segmentation by integrating the Spine-GANmethod and WOA. Here, the spinal cord images are segmented using the proposed WSpine-GAN method by tuning the weights optimally to enhance the performance of the disc segmentation.

scholarly journals Single Image Super-Resolution: Depthwise Separable Convolution Super-Resolution Generative Adversarial Network

2020 ◽  
Vol 10 (1) ◽  
pp. 375 ◽  
Author(s):  
Zetao Jiang ◽  
Yongsong Huang ◽  
Lirui Hu
Keyword(s):  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Features ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Visual Evaluation ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

The super-resolution generative adversarial network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied by unpleasant artifacts. To further enhance the visual quality, we propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The method is based on depthwise separable convolution super-resolution generative adversarial network (DSCSRGAN). A new depthwise separable convolution dense block (DSC Dense Block) was designed for the generator network, which improved the ability to represent and extract image features, while greatly reducing the total amount of parameters. For the discriminator network, the batch normalization (BN) layer was discarded, and the problem of artifacts was reduced. A frequency energy similarity loss function was designed to constrain the generator network to generate better super-resolution images. Experiments on several different datasets showed that the peak signal-to-noise ratio (PSNR) was improved by more than 3 dB, structural similarity index (SSIM) was increased by 16%, and the total parameter was reduced to 42.8% compared with the original model. Combining various objective indicators and subjective visual evaluation, the algorithm was shown to generate richer image details, clearer texture, and lower complexity.

scholarly journals GANai: Standardizing CT Images using Generative Adversarial Network with Alternative Improvement

2018 ◽  
Author(s):  
Gongbo Liang ◽  
Sajjad Fouladvand ◽  
Jie Zhang ◽  
Michael A. Brooks ◽  
Nathan Jacobs ◽  
...  
Keyword(s):  
Large Scale ◽  
Model Performance ◽  
Image Synthesis ◽  
Ct Images ◽  
Image Features ◽  
Training Data ◽  
Ct Image ◽  
Generative Adversarial Network ◽  
Training Strategy ◽  
Adversarial Network

AbstractComputed tomography (CT) is a widely-used diag-reproducibility regarding radiomic features, such as intensity, nostic image modality routinely used for assessing anatomical tissue characteristics. However, non-standardized imaging pro-tocols are commonplace, which poses a fundamental challenge in large-scale cross-center CT image analysis. One approach to address the problem is to standardize CT images using generative adversarial network models (GAN). GAN learns the data distribution of training images and generate synthesized images under the same distribution. However, existing GAN models are not directly applicable to this task mainly due to the lack of constraints on the mode of data to generate. Furthermore, they treat every image equally, but in real applications, some images are more difficult to standardize than the others. All these may lead to the lack-of-detail problem in CT image synthesis. We present a new GAN model called GANai to mitigate the differences in radiomic features across CT images captured using non-standard imaging protocols. Given source images, GANai composes new images by specifying a high-level goal that the image features of the synthesized images should be similar to those of the standard images. GANai introduces an alternative improvement training strategy to alternatively and steadily improve model performance. The new training strategy enables a series of technical improvements, including phase-specific loss functions, phase-specific training data, and the adoption of ensemble learning, leading to better model performance. The experimental results show that GANai is significantly better than the existing state-of-the-art image synthesis algorithms on CT image standardization. Also, it significantly improves the efficiency and stability of GAN model training.

scholarly journals Designed proteins assemble antibodies into modular nanocages

2020 ◽  
Author(s):  
Robby Divine ◽  
Ha V. Dang ◽  
George Ueda ◽  
Jorge A. Fallas ◽  
Ivan Vulovic ◽  
...  
Keyword(s):  
Computational Models ◽  
Computational Design ◽  
Covalent Modification ◽  
T Cell Proliferation ◽  
Surface Receptors ◽  
Form And Function ◽  
Designed Proteins ◽  
Cd40 Activation ◽  
And Function ◽  
Binding Avidity

AbstractAntibodies are widely used in biology and medicine, and there has been considerable interest in multivalent antibody formats to increase binding avidity and enhance signaling pathway agonism. However, there are currently no general approaches for forming precisely oriented antibody assemblies with controlled valency. We describe the computational design of two-component nanocages that overcome this limitation by uniting form and function. One structural component is any antibody or Fc fusion and the second is a designed Fc-binding homo-oligomer that drives nanocage assembly. Structures of 8 antibody nanocages determined by electron microscopy spanning dihedral, tetrahedral, octahedral, and icosahedral architectures with 2, 6, 12, and 30 antibodies per nanocage match the corresponding computational models. Antibody nanocages targeting cell-surface receptors enhance signaling compared to free antibodies or Fc-fusions in DR5-mediated apoptosis, Tie2-mediated angiogenesis, CD40 activation, and T cell proliferation; nanocage assembly also increases SARS-CoV-2 pseudovirus neutralization by α-SARS-CoV-2 monoclonal antibodies and Fc-ACE2 fusion proteins. We anticipate that the ability to assemble arbitrary antibodies without need for covalent modification into highly ordered assemblies with different geometries and valencies will have broad impact in biology and medicine.

scholarly journals KS(conf): A Light-Weight Test if a Multiclass Classifier Operates Outside of Its Specifications

2019 ◽  
Vol 128 (4) ◽  
pp. 970-995
Author(s):  
Rémy Sun ◽  
Christoph H. Lampert
Keyword(s):  
False Positive ◽  
False Positive Rate ◽  
A Priori ◽  
False Negative ◽  
True Positive Rate ◽  
Convolutional Network ◽  
The Road ◽  
Positive Rate ◽  
On The Road ◽  
Main Component

Abstract We study the problem of automatically detecting if a given multi-class classifier operates outside of its specifications (out-of-specs), i.e. on input data from a different distribution than what it was trained for. This is an important problem to solve on the road towards creating reliable computer vision systems for real-world applications, because the quality of a classifier’s predictions cannot be guaranteed if it operates out-of-specs. Previously proposed methods for out-of-specs detection make decisions on the level of single inputs. This, however, is insufficient to achieve low false positive rate and high false negative rates at the same time. In this work, we describe a new procedure named KS(conf), based on statistical reasoning. Its main component is a classical Kolmogorov–Smirnov test that is applied to the set of predicted confidence values for batches of samples. Working with batches instead of single samples allows increasing the true positive rate without negatively affecting the false positive rate, thereby overcoming a crucial limitation of single sample tests. We show by extensive experiments using a variety of convolutional network architectures and datasets that KS(conf) reliably detects out-of-specs situations even under conditions where other tests fail. It furthermore has a number of properties that make it an excellent candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with any classifier that outputs confidence scores, and requires no a priori knowledge about how the data distribution could change.

scholarly journals Classification of lung nodules using CT images based on texture features and fractal dimension transformation

2019 ◽  
Vol 485 (5) ◽  
pp. 558-563
Author(s):  
V. F. Kravchenko ◽  
V. I. Ponomaryov ◽  
V. I. Pustovoit ◽  
E. Rendon-Gonzalez
Keyword(s):  
Fractal Dimension ◽  
Block Diagram ◽  
False Positive Rate ◽  
A Priori ◽  
Lung Nodule ◽  
Texture Features ◽  
Lung Nodules ◽  
Cad System ◽  
Positive Rate ◽  
Priori Information

A new computer-aided detection (CAD) system for lung nodule detection and selection in computed tomography scans is substantiated and implemented. The method consists of the following stages: preprocessing based on threshold and morphological filtration, the formation of suspicious regions of interest using a priori information, the detection of lung nodules by applying the fractal dimension transformation, the computation of informative texture features for identified lung nodules, and their classification by applying the SVM and AdaBoost algorithms. A physical interpretation of the proposed CAD system is given, and its block diagram is constructed. The simulation results based on the proposed CAD method demonstrate advantages of the new approach in terms of standard criteria, such as sensitivity and the false-positive rate.

scholarly journals Designed proteins assemble antibodies into modular nanocages

Science ◽  
2021 ◽  
Vol 372 (6537) ◽  
pp. eabd9994
Author(s):  
Robby Divine ◽  
Ha V. Dang ◽  
George Ueda ◽  
Jorge A. Fallas ◽  
Ivan Vulovic ◽  
...  
Keyword(s):  
Computational Models ◽  
Death Receptor ◽  
Computational Design ◽  
Death Receptor 5 ◽  
Angiotensin Converting Enzyme 2 ◽  
Surface Receptors ◽  
Form And Function ◽  
Cd40 Activation ◽  
Multivalent Display ◽  
And Function

Multivalent display of receptor-engaging antibodies or ligands can enhance their activity. Instead of achieving multivalency by attachment to preexisting scaffolds, here we unite form and function by the computational design of nanocages in which one structural component is an antibody or Fc-ligand fusion and the second is a designed antibody-binding homo-oligomer that drives nanocage assembly. Structures of eight nanocages determined by electron microscopy spanning dihedral, tetrahedral, octahedral, and icosahedral architectures with 2, 6, 12, and 30 antibodies per nanocage, respectively, closely match the corresponding computational models. Antibody nanocages targeting cell surface receptors enhance signaling compared with free antibodies or Fc-fusions in death receptor 5 (DR5)–mediated apoptosis, angiopoietin-1 receptor (Tie2)–mediated angiogenesis, CD40 activation, and T cell proliferation. Nanocage assembly also increases severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pseudovirus neutralization by α-SARS-CoV-2 monoclonal antibodies and Fc–angiotensin-converting enzyme 2 (ACE2) fusion proteins.

scholarly journals HiCSR: a Hi-C super-resolution framework for producing highly realistic contact maps

2020 ◽  
Author(s):  
Michael C. Dimmick ◽  
Leo J. Lee ◽  
Brendan J. Frey
Keyword(s):  
High Resolution ◽  
Super Resolution ◽  
Cell Types ◽  
Supplementary Information ◽  
Low Resolution ◽  
Generative Adversarial Network ◽  
High Resolution Data ◽  
Contact Maps ◽  
Adversarial Network ◽  
And Function

AbstractMotivationHi-C data has enabled the genome-wide study of chromatin folding and architecture, and has led to important discoveries in the structure and function of chromatin conformation. Here, high resolution data plays a particularly important role as many chromatin substructures such as Topologically Associating Domains (TADs) and chromatin loops cannot be adequately studied with low resolution contact maps. However, the high sequencing costs associated with the generation of high resolution Hi-C data has become an experimental barrier. Data driven machine learning models, which allow low resolution Hi-C data to be computationally enhanced, offer a promising avenue to address this challenge.ResultsBy carefully examining the properties of Hi-C maps and integrating various recent advances in deep learning, we developed a Hi-C Super-Resolution (HiCSR) framework capable of accurately recovering the fine details, textures, and substructures found in high resolution contact maps. This was achieved using a novel loss function tailored to the Hi-C enhancement problem which optimizes for an adversarial loss from a Generative Adversarial Network (GAN), a feature reconstruction loss derived from the latent representation of a denoising autoencoder, and a pixel-wise loss. Not only can the resulting framework generate enhanced Hi-C maps more visually similar to the original high resolution maps, it also excels on a suite of reproducibility metrics produced by members of the ENCODE Consortium compared to existing approaches, including HiCPlus, HiCNN, hicGAN and DeepHiC. Finally, we demonstrate that HiCSR is capable of enhancing Hi-C data across sequencing depth, cell types, and species, recovering biologically significant contact domain boundaries.AvailabilityWe make our implementation available for download at: https://github.com/PSI-Lab/[email protected] informationAvailable Online

scholarly journals A method to adjust a prior distribution in Bayesian second-level fMRI analysis

2020 ◽  
Author(s):  
Hyemin Han
Keyword(s):  
Prior Distribution ◽  
Bayes Factor ◽  
Meta Analysis ◽  
False Positive Rate ◽  
A Priori ◽  
Correction Method ◽  
Positive Rate ◽  
Improved Performance ◽  
Fmri Analysis ◽  
Priori Information

Previous research has shown the potential value of Bayesian methods in fMRI (functional magnetic resonance imaging) analysis. For instance, the results from Bayes factor-applied second-level fMRI analysis showed a higher hit rate compared with frequentist second-level fMRI analysis, suggesting greater sensitivity. Although the method reported more positives as a result of the higher sensitivity, it was able to maintain a reasonable level of selectivity in term of the false positive rate. Moreover, employment of the multiple comparison correction method to update the default prior distribution significantly improved the performance of Bayesian second-level fMRI analysis. However, previous studies have utilized the default prior distribution and did not consider the nature of each individual study. Thus, in the present study, a method to adjust the Cauchy prior distribution based on a priori information, which can be acquired from the results of relevant previous studies, was proposed and tested. A Cauchy prior distribution was adjusted based on the contrast, noise strength, and proportion of true positives that were estimated from a meta-analysis of relevant previous studies. In the present study, both the simulated images and real contrast images from two previous studies were used to evaluate the performance of the proposed method. The results showed that the employment of the prior adjustment method resulted in improved performance of Bayesian second-level fMRI analysis.

scholarly journals A method to adjust a prior distribution in Bayesian second-level fMRI analysis

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e10861
Author(s):  
Hyemin Han
Keyword(s):  
Prior Distribution ◽  
Bayes Factor ◽  
Meta Analysis ◽  
False Positive Rate ◽  
A Priori ◽  
Correction Method ◽  
Positive Rate ◽  
Improved Performance ◽  
Fmri Analysis ◽  
Priori Information

Previous research has shown the potential value of Bayesian methods in fMRI (functional magnetic resonance imaging) analysis. For instance, the results from Bayes factor-applied second-level fMRI analysis showed a higher hit rate compared with frequentist second-level fMRI analysis, suggesting greater sensitivity. Although the method reported more positives as a result of the higher sensitivity, it was able to maintain a reasonable level of selectivity in term of the false positive rate. Moreover, employment of the multiple comparison correction method to update the default prior distribution significantly improved the performance of Bayesian second-level fMRI analysis. However, previous studies have utilized the default prior distribution and did not consider the nature of each individual study. Thus, in the present study, a method to adjust the Cauchy prior distribution based on a priori information, which can be acquired from the results of relevant previous studies, was proposed and tested. A Cauchy prior distribution was adjusted based on the contrast, noise strength, and proportion of true positives that were estimated from a meta-analysis of relevant previous studies. In the present study, both the simulated images and real contrast images from two previous studies were used to evaluate the performance of the proposed method. The results showed that the employment of the prior adjustment method resulted in improved performance of Bayesian second-level fMRI analysis.

Sign in / Sign up

Export Citation Format

Share Document